Search

Objective: The prognostic stratification for oral tongue squamous cell carcinoma (OTSCC) is heavily based on postoperative pathological depth of invasion (pDOI). This study aims to propose a preoperative MR T-staging system based on tumor size for non-pT4 OTSCC. Methods: Retrospectively, 280 patients with biopsy-confirmed, non-metastatic, pT1-3 OTSCC, treated between January 2010 and December 2017, were evaluated. Multiple MR sequences, including axial T2-weighted imaging (WI), unenhanced T1WI, and axial, fat-suppressed coronal, and sagittal contrast-enhanced (CE) T1WI, were utilized to measure radiological depth of invasion (rDOI), tumor thickness, and largest diameter. Intra-class correlation (ICC) and univariate and multivariate analyses were used to evaluate measurement reproducibility, and factors' significance, respectively. Cutoff values were established using an exhaustive method. Results: Intra-observer (ICC = 0.81–0.94) and inter-observer (ICC = 0.79–0.90) reliability were excellent for rDOI measurements, and all measurements were significantly associated with overall survival (OS) (all p <.001). Measuring the rDOI on axial CE-T1WI with cutoffs of 8 mm and 12 mm yielded an optimal MR T-staging system for rT1-3 disease (5-year OS of rT1 vs rT2 vs rT3: 94.0% vs 72.8% vs 57.5%). Using multivariate analyses, the proposed T-staging exhibited increasingly worse OS (hazard ratio of rT2 and rT3 versus rT1, 3.56 [1.35–9.6], p =.011; 4.33 [1.59–11.74], p =.004; respectively), which outperformed pathological T-staging based on nonoverlapping Kaplan–Meier curves and improved C-index (0.682 vs. 0.639, p <.001). Conclusions: rDOI is a critical predictor of OTSCC mortality and facilitates preoperative prognostic stratification, which should be considered in future oral subsite MR T-staging. Clinical relevance statement: Utilizing axial CE-T1WI, an MR T-staging system for non-pT4 OTSCC was developed by employing rDOI measurement with optimal thresholds of 8 mm and 12 mm, which is comparable with pathological staging and merits consideration in future preoperative oral subsite planning. Key Points: • Tumor morphology, measuring sequences, and observers could impact MR-derived measurements and compromise the consistency with histology. • MR-derived measurements, including radiological depth of invasion (rDOI), tumor thickness, and largest diameter, have a prognostic impact on OS (all p <.001). • rDOI with cutoffs of 8 mm and 12 mm on axial CE-T1WI is an optimal predictor of OS and could facilitate risk stratification in non-pT4 OTSCC disease. [ABSTRACT FROM AUTHOR]

To compare the oncological outcomes between microwave ablation (MWA) and surgical resection (SR) in patients with ovarian cancer liver metastasis (OCLM). In this retrospective study, a total of 29 female patients (mean age, 47.8 ± 12.9 years; range, 21–65 years) diagnosed with forty-three OCLM nodules between September 2008 and July 2016 were included. All patients with ovarian cancer received chemotherapy and cytoreductive surgery (CRS). Fifteen patients with 22 nodules underwent MWA, and 14 patients with 21 nodules underwent SR. Overall survival (OS), local tumor recurrence-free survival (LTRS), and operation-related parameters were compared between the two groups. Multivariate analyses were performed on clinicopathological variables to identify factors affecting OS and LTRS. The median follow-up time was 70.2 months (range, 12.1–107.2 months). Fourteen patients died during this period. The 1-, 3-, and 5-year OS and LTRS rates after MWA were comparable to those after SR (p =.198 and p =.889, respectively). Compared with the SR group, the MWA group had a shorter surgical time (p <.001), less estimated blood loss (p <.001), shorter postoperative hospitalization (p <.001) and fewer costs (p =.015). The multivariate analysis showed that old age (p =.001) was a predictor of poor OS and that intrahepatic tumor size (p =.005) and intrahepatic tumor number (p =.001) were predictors of poor LTRS. Percutaneous MWA had comparable oncologic outcomes with those of SR and could be a safe and effective treatment for OCLM. [ABSTRACT FROM AUTHOR]

Background: Image registration technology has become an important medical image preprocessing step with the wide application of computer‐aided diagnosis technology in various medical image analysis tasks. Purpose: We propose a multiscale feature fusion registration based on deep learning to achieve the accurate registration and fusion of head magnetic resonance imaging (MRI) and solve the problem that general registration methods cannot handle the complex spatial information and position information of head MRI. Methods: Our proposed multiscale feature fusion registration network consists of three sequentially trained modules. The first is an affine registration module that implements affine transformation; the second is to realize non‐rigid transformation, a deformable registration module composed of top‐down and bottom‐up feature fusion subnetworks in parallel; and the third is a deformable registration module that also realizes non‐rigid transformation and is composed of two feature fusion subnetworks in series. The network decomposes the deformation field of large displacement into multiple deformation fields of small displacement by multiscale registration and registration, which reduces the difficulty of registration. Moreover, multiscale information in head MRI is learned in a targeted manner, which improves the registration accuracy, by connecting the two feature fusion subnetworks. Results: We used 29 3D head MRIs for training and seven volumes for testing and calculated the values of the registration evaluation metrics for the new algorithm to register anterior and posterior lateral pterygoid muscles. The Dice similarity coefficient was 0.745 ± 0.021, the Hausdorff distance was 3.441 ± 0.935 mm, the Average surface distance was 0.738 ± 0.098 mm, and the Standard deviation of the Jacobian matrix was 0.425 ± 0.043. Our new algorithm achieved a higher registration accuracy compared with state‐of‐the‐art registration methods. Conclusions: Our proposed multiscale feature fusion registration network can realize end‐to‐end deformable registration of 3D head MRI, which can effectively cope with the characteristics of large deformation displacement and the rich details of head images and provide reliable technical support for the diagnosis and analysis of head diseases. [ABSTRACT FROM AUTHOR]

Purpose: To investigate the prognostic significance of MR-detected mandibular nerve involvement (MNI) and its value for induction chemotherapy (IC) administration in patients with nasopharyngeal carcinoma (NPC) and T4 disease. Methods: This retrospective study enrolled 792 non-metastatic, biopsy-proven NPC patients. Univariate and multivariate analysis were used to evaluate potential prognosticators. The inter-observer agreement was assessed by the kappa values. Results: MR-detected MNI was observed in 141 (72.3%) patients among 195 patients with T4 disease, with excellent agreement between the readers (kappa = 0.926). Patients with MR-detected MNI presented better 5-year overall survival (OS) (hazard ratio [HR], 0.40; P = 0.006) than those with MR-negative MNI. Of these patients, IC treatment was verified as an independent factor (HR: 0.35; P = 0.014) with preferable effect on OS. Conclusion: MR-detected MNI could serve as an independent favorable prognostic predictor for OS in NPC patients with stage T4, which should be considered for stratifying these patients for IC administration. [ABSTRACT FROM AUTHOR]

Objectives: Prognoses for nasopharyngeal carcinoma (NPC) between categories T2 and T3 in the Eighth American Joint Committee on Cancer (AJCC) staging system were overlapped. We explored the value of skull base invasion (SBI) subclassification in prognostic stratification and use of induction chemotherapy (IC) to optimize T2/T3 categorization for NPC patients. Methods: We retrospectively reviewed 1752 NPC patients from two hospitals. Eight skull base bone structures were evaluated. Survival differences were compared between slight SBI (T3 patients with pterygoid process and/or base of the sphenoid bone invasion only) and severe SBI (T3 patients with other SBIs) with or without IC using random matched-pair analysis. We calculated the prognosis and Harrel concordance index (C-index) for the revised T category and compared IC outcomes for the revised tumor stages. Results: Compared to severe SBI, slight SBI showed better 5-year overall survival (OS) (81.5% vs. 92.3%, p = 0.001) and progression-free survival (PFS) (71.5% vs. 83.0%, p = 0.002). Additional IC therapy did not significantly improve OS and PFS in slight SBI. The proposed T category separated OS, PFS, and locoregional recurrence-free survival in T2 and T3 categories with statistical significance. An improved C-index for OS prediction was observed in the proposed T category with combined confounding factors, compared to the AJCC T staging system (0.725 vs. 0.713, p = 0.046). The survival benefits of IC were more obvious in the advanced stage. Conclusions: NPC patients with slight SBI were recommended to downstage to T2 category. The adjustment for T category enabled better prognostic stratification and guidance for IC use. Key Points: • For nasopharyngeal carcinoma (NPC) patients in T3 category, slight skull base invasion was a significant positive predictor for OS and PFS. • NPC patients with slight SBI might not gain significant survival benefits from induction chemotherapy. • Downstaging slight SBI NPC patients to T2 category would make a more accurate risk stratification, improve the predicting performance in OS, and have a better guidance in the use of IC for patients in advanced stage. [ABSTRACT FROM AUTHOR]

Objectives: This study aimed to assess the prognostic value of quantitative cervical nodal necrosis (CNN) burden in N staging risk stratification in patients with nasopharyngeal carcinoma. Methods: Univariate and multivariate Cox regression models evaluated the association between lymph node variables based on MRI images and survival. Revisions for the N classification system were proposed and compared to the 8th edition AJCC staging system using Harrell's concordance index (C-index). The survival outcomes of induction chemotherapy plus concurrent chemoradiotherapy (CCRT) and CCRT alone in patients with multiple CNNs were compared. Results: In 1319 patients enrolled, CNN was not an independent prognostic factor for the main survival outcomes, but multiple CNNs (three or more necrotic nodes) were independent prognostic factors for distant metastasis-free survival (DMFS) (adjusted hazard ratio [HR], 2.05; p = 0.020) and progression-free survival (PFS) (HR, 1.78; p = 0.004), surpassing other nodal variables. On upgrading patients with multiple CNNs to revised N3 disease, the proposed N staging widened the differences in DMFS and PFS between N2 and N3 disease. The overall survival of patients with multiple CNNs who received CCRT plus induction chemotherapy was improved compared to that of those who received CCRT alone (76.1% vs. 55.7%; adjusted p = 0.030). Conclusions: Upgrading patients with multiple CNNs to stage N3 may improve prognostication of the current AJCC staging system. Multiple CNNs might be a potential marker for stratifying patients who would benefit from induction chemotherapy. Key Points: • Quantitatively assessed the prognostic value of CNN burden in patients with NPC. • Upgrading patients with multiple CNNs to stage N3 may improve prognostication. • Multiple CNNs may be used as a stratification marker for induction chemotherapy. [ABSTRACT FROM AUTHOR]

Objectives: Develop and evaluate a deep learning-based automatic meningioma segmentation method for preoperative meningioma differentiation using radiomic features.Methods: A retrospective multicentre inclusion of MR examinations (T1/T2-weighted and contrast-enhanced T1-weighted imaging) was conducted. Data from centre 1 were allocated to training (n = 307, age = 50.94 ± 11.51) and internal testing (n = 238, age = 50.70 ± 12.72) cohorts, and data from centre 2 external testing cohort (n = 64, age = 48.45 ± 13.59). A modified attention U-Net was trained for meningioma segmentation. Segmentation accuracy was evaluated by five quantitative metrics. The agreement between radiomic features from manual and automatic segmentations was assessed using intra class correlation coefficient (ICC). After univariate and minimum-redundancy-maximum-relevance feature selection, L1-regularized logistic regression models for differentiating between low-grade (I) and high-grade (II and III) meningiomas were separately constructed using manual and automatic segmentations; their performances were evaluated using ROC analysis.Results: Dice of meningioma segmentation for the internal testing cohort were 0.94 ± 0.04 and 0.91 ± 0.05 for tumour volumes in contrast-enhanced T1-weighted and T2-weighted images, respectively; those for the external testing cohort were 0.90 ± 0.07 and 0.88 ± 0.07. Features extracted using manual and automatic segmentations agreed well, for both the internal (ICC = 0.94, interquartile range: 0.88-0.97) and external (ICC = 0.90, interquartile range: 0.78-70.96) testing cohorts. AUC of radiomic model with automatic segmentation was comparable with that of the model with manual segmentation for both the internal (0.95 vs. 0.93, p = 0.176) and external (0.88 vs. 0.91, p = 0.419) testing cohorts.Conclusions: The developed deep learning-based segmentation method enables automatic and accurate extraction of meningioma from multiparametric MR images and can help deploy radiomics for preoperative meningioma differentiation in clinical practice.Key Points: • A deep learning-based method was developed for automatic segmentation of meningioma from multiparametric MR images. • The automatic segmentation method enabled accurate extraction of meningiomas and yielded radiomic features that were highly consistent with those that were obtained using manual segmentation. • High-grade meningiomas were preoperatively differentiated from low-grade meningiomas using a radiomic model constructed on features from automatic segmentation. [ABSTRACT FROM AUTHOR]

• The developed MLNs counting model demonstrated acceptable ability in NPC. • LNNs counted by AMLNC showed favorable discriminatory in predicting prognostic. • AMLNC may serve as a reference tool for younger radiologists to evaluate MLNs. The number of metastatic lymph nodes (MLNs) is crucial for the survival of nasopharyngeal carcinoma (NPC), but manual counting is laborious. This study aims to explore the feasibility and prognostic value of automatic MLNs segmentation and counting. We retrospectively enrolled 980 newly diagnosed patients in the primary cohort and 224 patients from two external cohorts. We utilized the nnUnet model for automatic MLNs segmentation on multimodal magnetic resonance imaging. MLNs counting methods, including manual delineation-assisted counting (MDAC) and fully automatic lymph node counting system (AMLNC), were compared with manual evaluation (Gold standard). In the internal validation group, the MLNs segmentation results showed acceptable agreement with manual delineation, with a mean Dice coefficient of 0.771. The consistency among three counting methods was as follows 0.778 (Gold vs. AMLNC), 0.638 (Gold vs. MDAC), and 0.739 (AMLNC vs. MDAC). MLNs numbers were categorized into three-category variable (1–4, 5–9, > 9) and two-category variable (<4, ≥ 4) based on the gold standard and AMLNC. These categorical variables demonstrated acceptable discriminating abilities for 5-year overall survival (OS), progression-free, and distant metastasis-free survival. Compared with base prediction model, the model incorporating two-category AMLNC-counting numbers showed improved C-indexes for 5-year OS prediction (0.658 vs. 0.675, P = 0.045). All results have been successfully validated in the external cohort. The AMLNC system offers a time- and labor-saving approach for fully automatic MLNs segmentation and counting in NPC. MLNs counting using AMLNC demonstrated non-inferior performance in survival discrimination compared to manual detection. [ABSTRACT FROM AUTHOR]

Purpose: Diagnosis of lymph node metastasis (LNM) is critical for patients with pancreatic ductal adenocarcinoma (PDAC). We aimed to build deep learning radiomics (DLR) models of dual-energy computed tomography (DECT) to classify LNM status of PDAC and to stratify the overall survival before treatment. Methods: From August 2016 to October 2020, 148 PDAC patients underwent regional lymph node dissection and scanned preoperatively DECT were enrolled. The virtual monoenergetic image at 40 keV was reconstructed from 100 and 150 keV of DECT. By setting January 1, 2021, as the cut-off date, 113 patients were assigned into the primary set, and 35 were in the test set. DLR models using VMI 40 keV, 100 keV, 150 keV, and 100 + 150 keV images were developed and compared. The best model was integrated with key clinical features selected by multivariate Cox regression analysis to achieve the most accurate prediction. Results: DLR based on 100 + 150 keV DECT yields the best performance in predicting LNM status with the AUC of 0.87 (95% confidence interval [CI]: 0.85–0.89) in the test cohort. After integrating key clinical features (CT-reported T stage, LN status, glutamyl transpeptadase, and glucose), the AUC was improved to 0.92 (95% CI: 0.91–0.94). Patients at high risk of LNM portended significantly worse overall survival than those at low risk after surgery (P = 0.012). Conclusions: The DLR model showed outstanding performance for predicting LNM in PADC and hold promise of improving clinical decision-making. [ABSTRACT FROM AUTHOR]

Objectives: To identify the prognosis of parapharyngeal space involvement (PPSI) based on the number of subspaces involved (pre-styloid space, carotid space (CS), areas outside the CS) and explore its significance for current T-staging in patients with nasopharyngeal carcinoma (NPC). Methods: PPSI was retrospectively identified in 1224 patients with non-disseminated NPC at two centers on MRI and separated into four invasion patterns: pattern A (only post-styloid space), pattern B (post-styloid space, CS extension), pattern C (post-styloid space, pre-styloid space extension), and pattern D (all spaces). The Kaplan–Meier analysis and multivariate Cox regression models were used. Results: PPSI was diagnosed in 63.4% of cases, with patterns A, B, C, and D in 14.3%, 3.8%, 25.3%, and 18.6% of cases, respectively. No prognostic heterogeneity was observed between pattern B and pattern C (p > 0.05). Thus, the degree of PPSI was based on the number of subspaces involved: grade 0 (none), grade 1 (one), grade 2 (two), and grade 3 (three), which could independently predict overall survival (OS) (p < 0.001). T3 patients with grade 0/1 PPSI (slight-T3) had a better prognosis than those with grade 2/3 PPSI (severe-T3) in terms of OS, locoregional-free survival (LRFS), and progression-free survival (PFS) (all p < 0.001), whose hazard ratios were higher and lower than those with T1 and T2, respectively. Combining the T2 and slight-T3 groups as the proposed T2 provided significant differences in OS, LRFS, and PFS between T2 and T3 (all p < 0.05). Conclusions: The risk of death increased with the number of parapharyngeal subspaces involved. The degree of PPSI is recommended to optimize T3 heterogeneity. Key Points: • Parapharyngeal space involvement was proposed to differentiate patient risk groups based on the number of involved subspaces: grade 0 (none), grade 1 (one), grade 2 (two), or grade 3 (three). • The degree of parapharyngeal space involvement was an independent negative prognosticator for OS. • The degree of parapharyngeal space involvement may influence T-staging in patients with nasopharyngeal carcinoma. [ABSTRACT FROM AUTHOR]

• Rulefit enables the utilization of logical associations behind structured MRI report for nasopharyngeal carcinoma in the forms of prognostic rules. • The Rules model using Rulefit achieved a better accuracy and generalizability than common models for the prediction of overall survival among advanced nasopharyngeal carcinoma, with the highest C-index of 0.711 in external testing cohort. • Significant survival benefit was achieved in high-risk group stratified by Rules model with additional induction chemotherapy treatment. Structured MRI report facilitate prognostic prediction for nasopharyngeal carcinoma (NPC). However, the intrinsic association among structured variables is not fully utilised. This study aimed to investigate the performance of a Rulefit-based model in feature integration behind structured MRI report and prognostic prediction in advanced NPC. We retrospectively enrolled 1207 patients diagnosed with non-metastatic advanced NPC from two centres, and divided into training (N = 544), internal testing (N = 367), and external testing (N = 296) cohorts. Machine learning algorithms including multivariate analysis, deep learning, Lasso, and Rulefit were used to establish corresponding prognostic models. The concordance indices (C- indices) of three clinical and six combined models with different algorithms for overall survival (OS) prediction were compared. Survival benefits of induction chemotherapy (IC) were calculated among risk groups stratified by different models. A website was established for individualised survival visualisation. Incorporating structured variables into Stage model significantly improved the prognostic prediction performance. Six prognostic rules with structured variables were identified by Rulefit. OS prediction of Rules model was comparable to Lasso model in internal testing cohort (C-index: 0.720 vs. 0.713, P = 0.100) and achieved the highest C-index of 0.711 in external testing cohort, indicating better generalisability. The Rules model stratified patients into risk groups with significant 5-year OS differences in each cohort, and revealed significant survival benefits from additional IC in high-risk group. The Rulefit-based Rules model, with the revelation of intrinsic associations behind structured variables, is promising in risk stratification and guiding individualised IC treatment for advanced NPC. [ABSTRACT FROM AUTHOR]

Objectives: The carotid space is an integral part of the parapharyngeal space, with ambiguous prognostic value for patients with nasopharyngeal carcinoma (NPC). This study aimed to investigate the prognostic significance of carotid space involvement (CSI) and propose a treatment strategy.Materials and Methods: This retrospective study enrolled 792 patients with biopsy-confirmed, non-distant metastatic NPC staged by magnetic resonance imaging before treatment. We used multivariable Cox regression models and Kaplan-Meier methods to assess the association between the variables and survival outcomes. A matched-pair method (1:1) was used to compare the survival differences between the patients with CSI treated with induction chemotherapy (ICT)and that of those who were not.Results: The incidence rate of CSI was 21.7 % (172/792). Multivariate analysis revealed that CSI was not an independent prognostic factor for survival outcomes in the 792 patients with NPC; however, the Chi-square test showed a different distribution of treatment strategies with ICT for patients with and without CSI. After stratification by ICT, CSI was an independent prognostic factor for overall survival (OS) (p = 0.049) in patients without ICT, but not for distant metastasis-free, local recurrence-free, or progression-free survival (p˃0.05). Additionally, ICT improved OS in patients with CSI (hazard ratio, 0.42; p = 0.019). Matched pair analysis showed that patients with CSI gained prolonged OS from ICT compared with the non-ICT group (88.4 % vs 69.4 %, p = 0.028).Conclusion: CSI was an independent negative prognostic factor for OS in patients with NPC without ICT and might be an imaging marker for identifying eligible candidates for ICT. [ABSTRACT FROM AUTHOR]

• The SeqSeg addresses the problem of background dominance to achieve accurate NPC detection and segmentation. • Intelligent deep Q-learning-based nasopharyngeal carcinoma detection model is proposed. • Experiments on a large dataset from multi-device and multi-center demonstrate the reliability of the proposed method. • Efficient reward function and exploration strategy boost NPC detectio performance. • Recurrent attention and dilated border weighted loss function foster NPC segmentation. [Display omitted] Reliable nasopharyngeal carcinoma (NPC) segmentation plays an important role in radiotherapy planning. However, recent deep learning methods fail to achieve satisfactory NPC segmentation in magnetic resonance (MR) images, since NPC is infiltrative and typically has a small or even tiny volume with indistinguishable border, making it indiscernible from tightly connected surrounding tissues from immense and complex backgrounds. To address such background dominance problems, this paper proposes a sequential method (SeqSeg) to achieve accurate NPC segmentation. Specifically, the proposed SeqSeg is devoted to solving the problem at two scales: the instance level and feature level. At the instance level, SeqSeg is forced to focus attention on the tumor and its surrounding tissue through the deep Q-learning (DQL)-based NPC detection model by prelocating the tumor and reducing the scale of the segmentation background. Next, at the feature level, SeqSeg uses high-level semantic features in deeper layers to guide feature learning in shallower layers, thus directing the channel-wise and region-wise attention to mine tumor-related features to perform accurate segmentation. The performance of our proposed method is evaluated by extensive experiments on the large NPC dataset containing 1101 patients. The experimental results demonstrated that the proposed SeqSeg not only outperforms several state-of-the-art methods but also achieves better performance in multi-device and multi-center datasets. [ABSTRACT FROM AUTHOR]

• A scale attention hourglass network was proposedfor landmark location, which can overcome the difficultiesof similar anatomical structures and different image parameters. • A two-step automatic location scheme of anatomical landmarks in 3D medical imagewas designed to obtain the coordinates of anatomical landmarks from 3D medical images. • Atransfer learning scheme is recruited to improve the efficiency of network training and reduce the amount of training data. • A semiautomatic delineation system is designedfor anatomical structure pointsin3D medical imageto reduce the workload of landmark delineation in medical image. An anatomical landmark is biologically meaningful point in medical images and often used for medical image registration. The purpose of this study is to automatically locate anatomical landmarks from 3D medical images. A two-step automatic location scheme of anatomical landmarks in 3D medical image was designed in this study. In the first step, the full convolutional neural network was used for slice detection from a 3D medical image. In the second step, the scale attention hourglass network was used for landmark location in the detected slice and could overcome the difficulty of similar anatomical structures and different image parameters. This method was implemented and tested on four stable anatomical landmarks in 3D head MRI. A total of 500 and 300 3D head volumes were used for training and testing, respectively. Results showed that the slice detection accuracy reached 85.7% and that the maximum location error was less than one slice. The average accuracy of the four anatomical landmarks in the detected slice reached 87.2%, and the spatial distance was 2.4 ± 2.4, which obtained better performance compared with hourglass network and feature pyramid networks. This method can be useful for locating anatomical landmarks in 3D head MRI and provides technical support for medical image registration and big data analysis. [ABSTRACT FROM AUTHOR]